IncRNA function prediction method based on graph attention, storage medium and equipment

Abstract

The invention discloses an lncRNA function prediction method based on graph attention, a storage medium and equipment, and belongs to the field of biological information technology. The method aims at solving the problem that in an existing lncRNA function prediction method, priori lncRNA function annotation data is little, protein function annotation data needs to be used for indirectly predicting the function of lncRNA, and consequently the accuracy rate is low. According to the method, firstly, a graph contrast learning method based on a cross attention mechanism is used for extracting multiple kinds of lncRNA similarity information, and a comprehensive similarity matrix is generated; then extracting features of GO terms in the GO graph by using a knowledge graph embedding model, and generating a GO semantic similarity matrix; and finally, constructing a GCN and GAT combined graph representation learning model to learn features of the lncRNA and the GO, and predicting GO function annotation information of the lncRNA by adopting a KAN classifier. According to the method provided by the invention, the accuracy of lncRNA function prediction can be effectively improved.

Description

Technical Field

[0001] The present invention belongs to the field of bioinformatics and relates to a lncRNA function prediction method, storage medium and equipment. Background Art

[0002] Long non-coding RNA (lncRNA) is an RNA transcript with a length of more than 200 nucleotides. They lack key properties, such as protein coding potential and sequence conservation, which are inevitable for functional roles. lncRNAs are widely involved in animal neural development, cell regulation, tumorigenesis and metastasis. In addition, human diseases and cancers are associated with mutations and dysregulation of lncRNAs. In genome-wide analyses of lncRNA stability, it was found that the half-life of lncRNAs varies widely, all of which indicate that lncRNAs have complex metabolism and a wide range of functions. Since lncRNAs play an important role in regulating biological activities, it is particularly important to determine the biological functions of lncRNAs.

[0003] Although a large number of lncRNAs have been identified so far, the functions of the vast majority of lncRNAs are unknown compared to protein-coding genes. The gap between the discovery rate and annotation rate of lncRNAs has led to a limited understanding of the functions of lncRNAs. Methods for annotating lncRNA functions can be divided into two categories: biological experimental methods and computational methods. Biological experimental methods can accurately determine the functions of lncRNAs, but the experiments are costly and time-consuming. Therefore, the development of computational alternatives for predicting lncRNA functions is an urgent requirement for lncRNA research. There are two types of lncRNA function prediction methods. The first is based on a computational framework, using hypergeometric tests, KATZ measurements, double random walks, matrix decomposition and other methods to calculate the association scores of lncRNAs and proteins, and predicting lncRNA functions based on the association scores and known protein-GO annotations; the second method is based on machine learning methods, extracting features through various means including RWR, AvgSim, Bayesian networks, LSTM, etc., and then training SVM, RF and other classifier models with the learned features for prediction.

[0004] However, due to the small number of experimentally verified lncRNA functions, most methods predict the GO annotation function of lncRNA through known protein-GO associations, which leads to the problem of low accuracy in lncRNA function prediction. Summary of the invention

[0005] The purpose of the present invention is to solve the problem that in the existing lncRNA function prediction method, there is little prior lncRNA function annotation data, and protein function annotation data need to be borrowed to indirectly predict the function of lncRNA, resulting in low accuracy.

[0006] A lncRNA function prediction method based on graph attention, comprising the following steps:

[0007] S1. The similarity matrix S of the three lncRNAs was obtained according to the co-expression of lncRNA, lncRNA-protein interaction, and lncRNA-miRNA interaction. L , S P and S M ; The embedded representation of lncRNA is obtained by GCN model and graph contrast learning method based on cross attention mechanism respectively. l 、z m and z p , based on z l 、z m and z p Get the lncRNA comprehensive similarity matrix M l ;

[0008] S2. Based on the GO semantic similarity calculation method in the GOGCN method, a knowledge graph embedding model is designed to learn the representation of GO terms; the semantic similarity between terms is calculated using the representation of the terms to obtain the GO similarity matrix M g ;

[0009] S3, construct training set and lncRNA-GO association matrix based on prior lncRNA-GO functional annotation data;

[0010] S4. Using a hybrid graph representation of GCN and GAT to learn the lncRNA comprehensive similarity matrix M l , GO similarity matrix M g Processing is performed to obtain lncRNA-GO fusion features; the obtained lncRNA-GO fusion features are input into the KAN classifier to obtain the predicted lncRNA-GO functional annotations; the specific process includes the following steps:

[0011] S41, lncRNA comprehensive similarity matrix M l , GO similarity matrix M g Input them into GCN to get the features H l (1) and H g (1) ;

[0012] S42, H l (1)and lncRNA similarity matrix M l Input into GAT to obtain the feature H optimized by the attention mechanism l (2) ; H g (1) and GO similarity matrix M g Input into GAT to obtain the feature H optimized by the attention mechanism g (2) ;

[0013] S43, H l (2) and M l Input into GCN to obtain the re-extracted feature H of the structural information after attention mechanism optimization l (3) ; H g (2) and M g Input into GCN to obtain the re-extracted feature H of the structural information after attention mechanism optimization g (3) ;

[0014] S44, H l (1) and H l (3) Input into CNN to get fusion feature X l , H g (1) and H g (3) Input into CNN to get fusion feature X g ; According to the fusion feature X l and X g Get the predicted preference matrix

[0015] The binary cross entropy loss function is used to measure the difference between U and the lncRNA-GO association matrix obtained in step S3; the final lncRNA feature representation X is obtained by minimizing the binary cross entropy loss function on the training set obtained in step S3. l and GO’s characteristic representation X g ;

[0016] S45, the lncRNA feature X obtained above l and GO feature X g They were concatenated to form the lncRNA-GO fusion signature, which was input into the KAN classifier to obtain the predicted lncRNA-GO functional annotation.

[0017] Furthermore, in step S1, the similarity matrix S of the three lncRNAs is obtained according to the co-expression of lncRNA, lncRNA-protein interaction, and lncRNA-miRNA interaction. L , S P and S M The process includes the following steps:

[0018] S11. Obtaining lncRNA co-expression similarity data: extracting lncRNA expression profiles, calculating the Pearson correlation coefficient between each pair of lncRNA expression profiles to represent the co-expression similarity of lncRNA S L ;

[0019] S12. Obtaining similarity data of lncRNA-miRNA interactions: Obtain a dataset of lncRNA-miRNA interaction data, obtain the association of each pair of lncRNA-miRNA based on whether there is an association in the dataset, and then calculate the Gaussian kernel similarity matrix between lncRNA and miRNA to represent the similarity of lncRNA-miRNA interactions. M ;

[0020] S13. Obtaining similarity data of lncRNA-protein interactions: Obtaining a dataset of lncRNA-protein interactions, obtaining the association of each pair of lncRNA-proteins based on whether there is a lncRNA-protein pair in the interaction dataset, and calculating the Gaussian kernel similarity matrix between lncRNA and protein to represent the similarity of lncRNA-protein interactions S P .

[0021] Furthermore, in step S1, the embedded representation z of lncRNA is obtained by using the GCN model and the graph contrast learning method based on the cross attention mechanism. l 、z m 、z p The process includes the following steps:

[0022] S14. lncRNA co-expression similarity matrix S L , similarity matrix S of lncRNA and protein interactions P , similarity matrix S of lncRNA and miRNA interactions M Input them into the GCN model respectively, and the corresponding GCN generates the corresponding feature representation y l ,y p ,y m ;

[0023] Then, the output features of GCN are cross-attention calculated, that is, the cross-attention calculations are performed between the three features; l For example, first, l Applied with y m and p The cross attention mechanism is used to input y m and p The information in y is integrated into l In this case, a new feature y′ is generated. l ;

[0024] The same method was used to obtain the characteristic y′ of lncRNA-miRNA m , lncRNA-protein features y′ p ;

[0025] S15. After obtaining three features through the cross attention mechanism, the feature pairs of the same node in different views are regarded as positive sample pairs to obtain the feature y′ l and feature y′ m Positive sample pairs, features y′ l and feature y′ p Positive sample pair, feature y′ m and feature y′ p There are three positive sample pairs; negative sample pairs are feature pairs between different nodes, according to y′ l , y′ m , y′ p The corresponding positive and negative sample pairs are used to obtain the lncRNA co-expression feature z by using graph contrast learning. l , Characteristics of lncRNA-miRNA m , lncRNA-protein characteristics p .

[0026] Furthermore, the graph contrast learning method is used to obtain the feature z of lncRNA co-expression l In the process, the contrast loss used is as follows:

[0027]

[0028] Among them, 1 [k≠i] represents the indicator function. When k≠i, the value of the indicator function is 1, which is used to calculate the similarity between node i and node k. When k=i, the value of the indicator function is 0, that is, the similarity between the same nodes is not calculated; y′ k Represents y l′[i] is the sample corresponding to the negative sample pair; N is the number of lncRNAs; τ is the temperature parameter used to adjust the distribution smoothness of the similarity calculation; sim(·) represents the similarity function between two features.

[0029] Furthermore, the step S1 described in the example based on z l 、z m and z p The process of obtaining the lncRNA comprehensive similarity matrix includes the following steps:

[0030] S16. Obtained the characteristics of lncRNA co-expression l , Characteristics of lncRNA-miRNA m , lncRNA-protein characteristics p After feature fusion, the three features are concatenated and fused into a feature representation Z = [z l ||z m ||z p ];

[0031] S17. According to the feature representation Z of lncRNA, the cosine similarity of the feature representation Z of each two lncRNAs is calculated to obtain the lncRNA comprehensive similarity matrix M l .

[0032] Furthermore, the process of designing a knowledge graph embedding model to learn the representation of GO terms in step S2 includes the following steps:

[0033] S21, obtain GO file;

[0034] S22, represent the GO graph as G = (V, R, E, X, Z), where V is an entity set, representing GO terms; R is a relationship set; E represents an edge set; X represents an initialized entity representation, and Z represents an initialized relationship representation;

[0035] S23, in order to obtain the structural information of the GO graph, the encoder adds the propagation weight of the GCN layer on the basis of COMPGCN, and uses the inverse edges and relations to represent the extended edges and relations;

[0036] In S24, in the decoder, the GO graph is regarded as a triple, and the corresponding representation of the triple is used to train the link prediction model; in the training stage, a 1-n scoring strategy is adopted to generate damaged triples by destroying the head term or the tail term, and ConvE is used as the scoring function to provide higher scores for the real triples and lower scores for the damaged triples. The model converges to obtain the embedded representation of the GO terms;

[0037] S25. After training, the cosine similarity is used to estimate the semantic similarity between entities for the representation of GO terms, and then the GO similarity matrix M is obtained.g .

[0038] Furthermore, the process of constructing a training set based on prior lncRNA-GO functional annotation data described in step S3 includes the following steps:

[0039] First, obtain the lncRNA function annotation file predicted by the lnc-GFP method, and use the lncRNA-GO function annotation pairs in the predicted lncRNA function annotation file as positive samples;

[0040] S32. Randomly construct lncRNA-GO non-functional annotation pairs with the same number as lncRNA-GO functional annotation pairs as negative samples; lncRNA-GO functional annotation pairs and non-functional annotation pairs with the same number as lncRNA-GO functional annotation pairs form a training set.

[0041] Furthermore, the process of constructing the lncRNA-GO association matrix based on the prior lncRNA-GO functional annotation data described in step S3 includes the following steps:

[0042] According to the predicted lncRNA functional annotation file, the lncRNA-GO association matrix was constructed, in which 1 represents the lncRNA-GO functional annotation pair and 0 represents the lncRNA-GO non-functional annotation pair.

[0043] A computer storage medium stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement the lncRNA function prediction method based on graph attention.

[0044] A device for predicting lncRNA function based on graph attention, the device comprising a processor and a memory, the memory storing at least one instruction, the at least one instruction being loaded and executed by the processor to implement the method for predicting lncRNA function based on graph attention.

[0045] The beneficial effects of the present invention are:

[0046] The present invention uses a graph contrast learning method based on a cross-attention mechanism to extract lncRNA features, uses a knowledge graph embedding model to extract GO features, and uses a graph representation learning model combining GCN and GAT to predict lncRNA-GO functional annotations. Therefore, the present invention can effectively solve the problem that there is little prior lncRNA functional annotation data, and it is necessary to borrow protein functional annotation data to indirectly predict the function of lncRNA, resulting in low accuracy. Compared with other advanced models, the present invention has better prediction accuracy and model generalization, and provides effective technical support for discovering potential lncRNA functional annotations. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Flow chart of lncRNA function prediction based on graph attention;

[0048] Figure 2 This is the ablation result diagram of the cross-attention based graph contrast learning method;

[0049] Figure 3 PR curve of ablation results of the cross-attention-based graph contrast learning method;

[0050] Figure 4 This is the ablation result diagram of the network model combining GCN and GAT;

[0051] Figure 5 PR curve of the network model combining GCN and GAT;

[0052] Figure 6 Schematic diagram of the impact of different classifiers on the performance of lncRNA function prediction;

[0053] Figure 7 GO term depth and F1 graph under different classifiers;

[0054] Figure 8 IC and F1 graphs of GO terms under different classifiers;

[0055] Fig. 9 It is a PR curve comparison diagram of the present invention and related lncRNA function prediction models. DETAILED DESCRIPTION

[0056] In order to more clearly describe the present invention and introduce the purpose and technology of the present invention, the present invention will be further described below in combination with relevant data, drawings and examples. In particular, the description here is a specific example of part of the present invention, rather than limiting the scope of the invention.

[0057] Specific implementation method 1: Combination Figure 1 To explain this embodiment,

[0058] This embodiment provides a lncRNA function prediction method based on graph attention, comprising the following steps S1 to S5:

[0059] S1. Obtain the similarity matrix of three lncRNAs based on the co-expression of lncRNA, lncRNA-protein interaction, and lncRNA-miRNA interaction; obtain the embedded representation of lncRNA through the graph contrast learning method based on the cross-attention mechanism; and calculate the lncRNA comprehensive similarity matrix. The specific process includes the following steps:

[0060] S11. Obtaining lncRNA co-expression similarity data: Extracting lncRNA expression profiles from the NONCODE database, and calculating the Pearson correlation coefficient between each pair of lncRNA expression profiles to represent the co-expression similarity of lncRNA S L .

[0061] S12. Obtain similarity data of lncRNA-miRNA interactions: lncRNA-miRNA interaction data were obtained through the starBase database. If there was an association in the data set, the score was set to 1, otherwise it was set to 0. After obtaining the score of each pair of lncRNA-miRNA, the Gaussian kernel similarity matrix between lncRNA and miRNA was calculated to represent the similarity of lncRNA-miRNA interactions. M .

[0062] S13. Obtain similarity data of lncRNA-protein interactions: Obtain lncRNA-protein interactions through the NPInter database. If there are lncRNA-protein pairs in the interaction dataset, set their interaction scores to 1, otherwise set them to 0. After obtaining the scores of each pair of lncRNA-protein, calculate the Gaussian kernel similarity matrix between lncRNA and protein to represent the similarity of lncRNA-protein interactions S P .

[0063] S14. lncRNA co-expression similarity matrix S L , similarity matrix S of lncRNA and protein interactions P , similarity matrix S of lncRNA and miRNA interactions M Input them into the GCN model respectively, and the corresponding GCN generates the corresponding feature representation y l ,y p ,y m :

[0064] y l =GCN(s l ,A l )

[0065] y m =GCN(s m ,A m )

[0066] y p =GCN(s p ,A p )

[0067] Among them, s l Represents the graph corresponding to the lncRNA co-expression similarity matrix, sp The graph corresponding to the similarity matrix representing the interaction between lncRNA and protein, s m A graph showing the similarity matrix of the interaction between lncRNA and miRNA; l , A m , A p They are l 、s m 、s p The adjacency matrix of .

[0068] Then, the cross attention calculation is performed on the output features of GCN, that is, the cross attention calculation is performed between the three features. l For example, first, l Applied with y m and p The cross attention mechanism is used to input y m and p The information in y is integrated into l In this case, a new feature y′ is generated. l .

[0069] The same method was used to obtain the characteristic y′ of lncRNA-miRNA m , lncRNA-protein features y′ p .

[0070] y′ l =CrossAttention(y l ,y m ,y p )

[0071] y′ m =CrossAttention(y m ,y p ,y l )

[0072] y′ p =CrossAttention(y p ,y l ,y m )

[0073] S15. After obtaining three features through the cross attention mechanism, the feature pairs of the same node in different views are regarded as positive sample pairs, and the feature y′ can be obtained. l and feature y′ m Positive sample pairs, features y′ l and feature y′ p Positive sample pair, feature y′ m and feature y′ pThere are three types of positive sample pairs. Negative sample pairs are feature pairs between different nodes, regardless of whether these nodes are from the same view or different views. According to y′ l , y′ m , y′ p The corresponding positive and negative sample pairs are used to obtain the lncRNA co-expression feature z based on the contrast loss function NT-Xent. l , Characteristics of lncRNA-miRNA m , lncRNA-protein characteristics p .

[0074] Based on lncRNA co-expression comparison loss function L l Obtaining lncRNA co-expression characteristics l The process includes:

[0075] In the calculation of lncRNA co-expression contrast loss, for node i, the positive sample pair includes y′ l [i] and y′ m [i],y′ l [i] and y′ p [i], negative sample pairs represent feature pairs between different nodes. By maximizing the similarity of positive sample pairs and minimizing the similarity of negative sample pairs, the feature z of lncRNA co-expression is finally obtained after training. l .

[0076]

[0077] Among them, when k≠i, the indicator function 1 [k≠i] The value of is 1, which is used to calculate the similarity between node i and node k. When k = i, the value of the indicator function is 0, that is, the similarity between the same nodes is not calculated, regardless of whether the nodes are from the same view; y′ k Represents y′ l [i] is the sample corresponding to the negative sample pair; N is the number of lncRNAs; τ is the temperature parameter used to adjust the distribution smoothness of the similarity calculation; sim(·) represents the similarity function between two features, which is expressed by the following formula:

[0078]

[0079] Among them, ‖y' j ‖ represents the second norm.

[0080] The same method was used to obtain the characteristics of lncRNA-miRNA m , lncRNA-protein characteristics p .

[0081] After comparing the loss function NT-Xent, three features z are obtained. l 、z m 、z p .

[0082] S16. Obtained the characteristics of lncRNA co-expression l , Characteristics of lncRNA-miRNA m , lncRNA-protein characteristics p After feature fusion, the three features are concatenated and fused into a feature representation Z = [z l ||z m ||z p ].

[0083] S17. According to the feature representation Z of lncRNA, the cosine similarity of the feature representation Z of each two lncRNAs is calculated to obtain the lncRNA comprehensive similarity matrix M l .

[0084] S2. Based on the GO semantic similarity calculation method in the GOGCN method, a knowledge graph embedding model is designed to learn the representation of GO terms; the semantic similarity between terms is calculated using the representation of the terms. The GO semantic similarity calculation method in the GOGCN method can be implemented using "GOGCN: graph convolutional network on gene ontology for functional similarity analysis of genes" by Tian Z et al. The process of designing a knowledge graph embedding model to learn the representation of GO terms includes the following steps:

[0085] S21. GO files can be downloaded from the Gene Ontology database.

[0086] S22. Represent the GO graph as G = (V, R, E, X, Z), where V is the entity set, representing the GO terms; R is the relationship set, representing the two relationships "is_a" and "part_of"; E represents the edge set; X represents the initialized entity representation, and Z represents the initialized relationship representation.

[0087] S23. To obtain the structural information of the GO graph, the encoder adds the propagation weights of the GCN layer on the basis of COMPGCN, and uses the inverse edges and relations to represent the extended edges and relations. The encoder adds the propagation weights of the GCN layer on the basis of COMPGCN using the "Composition-based multi-relational graph convolutionalnetworks" by Vashishth S et al.

[0088] In S24, the decoder treats the GO graph as a triple, and uses the corresponding representation of the triple to train the link prediction model. In the training phase, a 1-n scoring strategy is used to generate corrupted triples by destroying the head term or the tail term. ConvE is used as the scoring function to provide higher scores for true triples and lower scores for corrupted triples. The model converges to obtain the embedded representation of the GO terms.

[0089] S25. After training, the cosine similarity is used to estimate the semantic similarity between entities for the representation of GO terms, and then the GO similarity matrix M is obtained. g .

[0090] S3. Collect and organize prior lncRNA-GO functional annotation data, and construct a training set and lncRNA-GO association matrix. The specific process includes the following steps:

[0091] S31. Obtain the lncRNA function annotation file predicted by the lnc-GFP method, and use the lncRNA-GO function annotation pair in the predicted lncRNA function annotation file as a positive sample; the lncRNA function annotation file predicted by the lnc-GFP method was obtained through "Long non-coding RNAs function annotation: a global prediction method based on bi-colored networks" by GuoX et al.

[0092] S32. In order to balance the number of positive and negative samples in the training set, randomly construct lncRNA-GO non-functional annotation pairs equal to the number of lncRNA-GO functional annotation pairs as negative samples; lncRNA-GO functional annotation pairs and non-functional annotation pairs equal to the number of lncRNA-GO functional annotation pairs form the training set.

[0093] S33. Based on the predicted lncRNA functional annotation file, a lncRNA-GO association matrix was constructed, in which 1 represents a lncRNA-GO functional annotation pair and 0 represents a lncRNA-GO non-functional annotation pair.

[0094] S4. In order to fully learn the feature representation of lncRNA and GO, a hybrid graph representation combining GCN and GAT is used to learn the lncRNA comprehensive similarity matrix M l , GO similarity matrix M g Processing is performed to obtain lncRNA-GO fusion features; the obtained lncRNA-GO fusion features are input into the KAN classifier to obtain the predicted lncRNA-GO functional annotations; the specific process includes the following steps:

[0095] S41, lncRNA comprehensive similarity matrix M l , GO similarity matrix M g Input them into GCN to obtain the features H with general neighbor aggregation information l (1) and H g (1) .

[0096] S42, H l (1) and lncRNA similarity matrix M l Input into GAT to obtain the feature H optimized by the attention mechanism l (2) ; H g (1) and GO similarity matrix M g Input into GAT to obtain the feature H optimized by the attention mechanism g (2) .

[0097] S43, H l (2) and M l Input into GCN to obtain the re-extracted feature H of the structural information after attention mechanism optimization l (3) ; H g (2) and M g Input into GCN to obtain the re-extracted feature H of the structural information after attention mechanism optimization g (3) .

[0098] Taking lncRNA feature acquisition as an example, H l (0) Represents the lncRNA node features of the lncRNA similarity network input. Then GCN and GAT are introduced alternately to obtain lncRNA feature representations at different levels.

[0099]

[0100] Among them, M l is the adjacency matrix of the lncRNA similarity network.

[0101] S44, H l (1) and H l (3) Input into CNN to get fusion feature X l , H g (1) and H g(3) Input into CNN to get fusion feature X g ; According to the fusion feature X l and X g Get the predicted preference matrix U:

[0102]

[0103] The binary cross entropy loss function (BCE loss function) is used to measure the difference between U and the known lncRNA-GO association matrix. By minimizing the BCE loss function in the training set (the training set obtained in S3), the final lncRNA feature representation X can be obtained. l and GO’s characteristic representation X g .

[0104] S45, the lncRNA feature X obtained above l and GO feature X g They were concatenated to form the lncRNA-GO fusion signature, which was input into the KAN classifier to obtain the predicted lncRNA-GO functional annotation.

[0105] S5. Conduct comparative experiments and ablation experiments on commonly used public test datasets, collect and organize the experimental results; use indicators such as AUPR (area under the PR curve), precision, recall, F1-score, and accuracy to analyze the experimental results from multiple angles to evaluate the performance of the new method.

[0106] S51. The performance of the present invention on the training set and the independent test set lncRNA2GO-55 is compared using a graph contrast learning method without cross-attention, a graph contrast learning method without GCN, a network model without GAT, and the present method, respectively. The evaluation indicators used include AUPR (area under the PR curve), precision, recall, F1-score, and accuracy.

[0107] S52. The performance of the present invention and the HLPFN, KATZLGO, BIRWLGO, DNGRGO, and PLNRGO related models on the independent test set lncRNA2GO-55 were compared, and the evaluation indicators used included precision, recall, and F1 score.

[0108] The specific calculation formula is as follows:

[0109]

[0110] Among them, TP is true positive, indicating the number of correctly predicted lncRNA-GO associations; FP is false positive, indicating the number of incorrectly predicted lncRNA-GO associations; TN is true negative, indicating the number of correctly predicted non-lncRNA-GO associations; FN is false negative, indicating the number of incorrectly predicted non-lncRNA-GO associations.

[0111] The recognition effect of the present invention is further described below with a group of specific experimental examples.

[0112] In order to evaluate the effect of graph contrast learning method based on cross-attention mechanism on the prediction performance of lncRNA function, this example established a prediction method that directly integrates three similarity matrices to represent the similarity of lncRNA (lncRNA-TSIM), a prediction method that only uses graph contrast learning to extract lncRNA features (lncRNA-GraphCL), and a prediction method that uses graph contrast learning based on cross-attention mechanism to extract lncRNA features (lncRNA-CA-GraphCL). And the performance on independent test sets is compared. Figure 2-Figure 3 As shown ( Figure 2 The order of the five columns in each method from left to right is Accuracy, Precision, Recall, F1, AUPRC, Figure 3 The PR curve indicates that the performance of the present invention on the independent test set is better than that of other models. This shows that the graph contrast learning method based on the cross-attention mechanism can more effectively extract the features of lncRNA.

[0113] In order to evaluate the effect of the graph representation learning model combining GCN and GAT on the performance of lncRNA function prediction, this example established a graph representation learning model with only GCN (GraphGCN), a graph representation learning model with only GAT (GraphGAT), and a graph representation learning model with GCN and GAT (GraphGCN-GAT, this model), and compared their performance on an independent test set. Figure 4-Figure 5 As shown ( Figure 4 The order of the five columns in each method from left to right is Accuracy, Precision, Recall, F1, AUPRC, Figure 5The performance of the present invention on the independent test set is better than that of other models, among which the F1 of the present invention is slightly higher than that of other methods, but the Accuracy, Precision, and AUPRC of the present invention are significantly higher than those of other methods. This shows that the graph representation learning model combining GCN and GAT can effectively integrate representations at all levels and can effectively improve the representation learning ability of lncRNA and GO.

[0114] In order to determine the most suitable classifier for the present invention, various machine learning-based models were tested, such as random forest (RF), support vector machine (SVM), decision tree (DT), logistic regression (LR), adaptive boosting (AdaBoost), multilayer perceptron (MLP), K nearest neighbor algorithm (KNN), Kolmogorov-Arnold Networks (KAN). Different classifiers were used to verify the performance on independent test sets to predict lncRNA-GO functional annotations. Figure 6 As shown, the model using KAN as the final classifier significantly outperforms other methods in the distribution of AUPRC values. This indicates that the KAN classifier is more suitable for the present invention than other tested algorithms for predicting the association of lncRNA with GO.

[0115] To explain the results in more depth, Figure 7-Figure 8 The F1-GO depth and F1-IC of different classifiers on independent test sets are shown. Because GO terms have depth and breadth, the closer to the root node, the lower the meaning of the predicted GO terms. Therefore, the IC value of each GO term needs to be calculated. The IC value is calculated as follows:

[0116]

[0117] Among them, depth(term) indicates the depth of the term in the GO graph, max_depth is the maximum depth of the term in the GO graph, descendants(term) is the number of the term and all its descendant terms, and total_terms is the total number of all terms in the GO graph. It can be seen that the KAN classifier performs better in almost all levels of prediction.

[0118] In order to verify the superior performance of the present invention, the present invention, HLPFN, KATZLGO, BIRWLGO, DNGRGO, PLNRGO and other methods were used to perform lncRNA function prediction tasks on the test data set, and their prediction results were analyzed to obtain the performance as follows: Fig. 9 The present invention performs better than similar methods and has better prediction performance.

[0119] In order to verify the application effect of the present invention in actual cases, three lncRNAs, NEAT1, GHET1, and HOTAIRM1, are used as examples to further demonstrate the prediction performance and demonstrate the application of our method. This case study focuses on the predicted functional associations of the three lncRNAs established. The top 20 functions of NEAT1 predicted by the model are shown in Table 1. The study predicted 48 GO terms and successfully predicted 37 functional associations of NEAT1, of which NEAT1 had 38 GO term annotations. The predicted top 20 functions of GHET1 are shown in Table 2. The study predicted 34 GO terms and successfully predicted 21 functional associations of GHET1, of which the lncRNA had 23 GO terms. The predicted top 20 functions of HOTAIRM1 are shown in Table 3. The study predicted 22 GO terms and successfully predicted 10 functional associations of HOTAIRM1, of which the lncRNA had 10 GO terms.

[0120] Table 1 Verification of the top 20 GOs predicted by the present invention to be associated with NEAT1

[0121]

[0122]

[0123] Table 2 Verification of the top 20 GOs predicted by the present invention to be associated with GHET1

[0124]

[0125] Table 3 Verification of the top 20 GOs predicted by the present invention to be associated with HOTAIRM1

[0126]

[0127] Specific implementation method 2:

[0129] This embodiment is a computer storage medium, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement the lncRNA function prediction method based on graph attention.

[0130] It should be understood that the instructions include computer program products, software or computerized methods corresponding to any method described in the present invention; the instructions can be used to program a computer system, or other electronic device. Computer storage media may include readable media on which instructions are stored, which may include but are not limited to magnetic storage media, optical storage media; magneto-optical storage media include read-only memory ROM, random access memory RAM, erasable programmable memory (e.g., EPROM and EEPROM) and flash memory layers, or other types of media suitable for storing electronic instructions. Specific implementation method three:

[0132] This embodiment is a lncRNA function prediction device based on graph attention, the device includes a processor and a memory. It should be understood that including any device including a processor and a memory described in the present invention, the device may also include other units and modules that perform display, interaction, processing, control, etc. and other functions through signals or instructions;

[0133] At least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement the lncRNA function prediction method based on graph attention.

[0134] Those skilled in the art will appreciate that at least one instruction stored is a computer program product corresponding to the method or system. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The scheme in the embodiment of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0135] The present application is described with reference to the flowcharts and / or block diagrams of the methods, systems, and computer program products according to the embodiments of the present application, and may also be used for corresponding devices. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0136] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0138] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0139] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0140] The above calculation examples of the present invention are only used to explain the calculation model and calculation process of the present invention in detail, and are not intended to limit the implementation methods of the present invention. For ordinary technicians in the relevant field, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the implementation methods here. All obvious changes or modifications derived from the technical solution of the present invention are still within the scope of protection of the present invention.

Claims

1. A lncRNA function prediction method based on graph attention, characterized in that: The following steps are involved: S1. The similarity matrix S of the three lncRNAs was obtained according to the co-expression of lncRNA, lncRNA-protein interaction, and lncRNA-miRNA interaction. L , S P and S M ; The embedded representation of lncRNA is obtained by GCN model and graph contrast learning method based on cross attention mechanism respectively. l 、z m and z p , based on z l 、z m and z p Get the lncRNA comprehensive similarity matrix M l ; S2. Based on the GO semantic similarity calculation method in the GOGCN method, a knowledge graph embedding model is designed to learn the representation of GO terms; the semantic similarity between terms is calculated using the representation of the terms to obtain the GO similarity matrix M g ; S3, construct training set and lncRNA-GO association matrix based on prior lncRNA-GO functional annotation data; S4. Using a hybrid graph representation of GCN and GAT to learn the lncRNA comprehensive similarity matrix M l , GO similarity matrix M g Processing is performed to obtain lncRNA-GO fusion features; the obtained lncRNA-GO fusion features are input into the KAN classifier to obtain the predicted lncRNA-GO functional annotations; The specific process includes the following steps: S41, lncRNA comprehensive similarity matrix M l , GO similarity matrix M g Input them into GCN to get the features H l (1) and H g (1) ; S42, H l (1) and lncRNA similarity matrix M l Input into GAT to obtain the feature H optimized by the attention mechanism l (2) ; H g (1) and GO similarity matrix M g Input into GAT to obtain the feature H optimized by the attention mechanism g (2) ; S43, H l (2) and M l Input into GCN to obtain the re-extracted feature H of the structural information after attention mechanism optimization l (3) ; H g (2) and M g Input into GCN to obtain the re-extracted feature H of the structural information after attention mechanism optimization g (3) ; S44, H l (1) and H l (3) Input into CNN to get fusion feature X l , H g (1) and H g (3) Input into CNN to get fusion feature X g ; According to the fusion feature X l and X g Get the predicted preference matrix U = X l T X g ; The binary cross entropy loss function is used to measure the difference between U and the lncRNA-GO association matrix obtained in step S3; the final lncRNA feature representation X is obtained by minimizing the binary cross entropy loss function on the training set obtained in step S3. l and GO’s characteristic representation X g ; S45, the lncRNA feature X obtained above l and GO feature X g They were concatenated to form the lncRNA-GO fusion signature, which was input into the KAN classifier to obtain the predicted lncRNA-GO functional annotation.

2. The lncRNA function prediction method based on graph attention according to claim 1, characterized in that: The similarity matrix S of the three lncRNAs is obtained according to the co-expression of lncRNA, lncRNA-protein interaction, and lncRNA-miRNA interaction described in step S1. L , S P and S M The process includes the following steps: S11. Obtaining lncRNA co-expression similarity data: extracting lncRNA expression profiles, calculating the Pearson correlation coefficient between each pair of lncRNA expression profiles to represent the co-expression similarity of lncRNA S L ; S12. Obtaining similarity data of lncRNA-miRNA interactions: Obtain a dataset of lncRNA-miRNA interaction data, obtain the association of each pair of lncRNA-miRNA based on whether there is an association in the dataset, and then calculate the Gaussian kernel similarity matrix between lncRNA and miRNA to represent the similarity of lncRNA-miRNA interactions. M ; S13. Obtaining similarity data of lncRNA-protein interactions: Obtaining a dataset of lncRNA-protein interactions, obtaining the association of each pair of lncRNA-proteins based on whether there is a lncRNA-protein pair in the interaction dataset, and calculating the Gaussian kernel similarity matrix between lncRNA and protein to represent the similarity of lncRNA-protein interactions S P .

3. The lncRNA function prediction method based on graph attention according to claim 1, characterized in that: The embedded representation z of lncRNA is obtained by the GCN model and the graph contrast learning method based on the cross attention mechanism as described in step S1. l 、z m 、z p The process includes the following steps: S14. lncRNA co-expression similarity matrix S L , similarity matrix S of lncRNA and protein interactions P , similarity matrix S of lncRNA and miRNA interactions M Input them into the GCN model respectively, and the corresponding GCN generates the corresponding feature representation y l ,y p ,y m ; Then, the output features of GCN are cross-attention calculated, that is, the cross-attention calculations are performed between the three features; l For example, first, l Applied with y m and p The cross attention mechanism is used to input y m and p The information in y is integrated into l In this case, a new feature y′ is generated. l ; The same method was used to obtain the characteristic y′ of lncRNA-miRNA m , lncRNA-protein features y′ p ; S15. After obtaining three features through the cross attention mechanism, the feature pairs of the same node in different views are regarded as positive sample pairs to obtain the feature y′ l and feature y′ m Positive sample pairs, features y′ l and feature y′ p Positive sample pair, feature y′ m and feature y′ p There are three positive sample pairs; negative sample pairs are feature pairs between different nodes, according to y′ l , y′ m , y′ p The corresponding positive and negative sample pairs are used to obtain the lncRNA co-expression feature z by using graph contrast learning. l , Characteristics of lncRNA-miRNA m , lncRNA-protein characteristics p .

4. The lncRNA function prediction method based on graph attention according to claim 3, characterized in that: The feature z of lncRNA co-expression is obtained by graph contrast learning. l In the process, the contrast loss used is as follows: Among them, 1 [k≠i] represents the indicator function. When k≠i, the value of the indicator function is 1, which is used to calculate the similarity between node i and node k. When k=i, the value of the indicator function is 0, that is, the similarity between the same nodes is not calculated; y′ k Represents y l ′[i] is the sample corresponding to the negative sample pair; N is the number of lncRNAs; τ is the temperature parameter used to adjust the distribution smoothness of the similarity calculation; sim(·) represents the similarity function between two features.

5. The lncRNA function prediction method based on graph attention according to claim 1, characterized in that: Step S1 described in z l 、z m and z p The process of obtaining the lncRNA comprehensive similarity matrix includes the following steps: S16. Obtained the characteristics of lncRNA co-expression l , Characteristics of lncRNA-miRNA m , lncRNA-protein characteristics p After feature fusion, the three features are concatenated and fused into a feature representation Z = [z l ||z m ||z p ]; S17. According to the feature representation Z of lncRNA, the cosine similarity of the feature representation Z of each two lncRNAs is calculated to obtain the lncRNA comprehensive similarity matrix M l .

6. The lncRNA function prediction method based on graph attention according to claim 1, characterized in that: The process of designing a knowledge graph embedding model to learn the representation of GO terms in step S2 includes the following steps: S21, obtain GO file; S22, represent the GO graph as G = (V, R, E, X, Z), where V is an entity set, representing GO terms; R is a relationship set; E represents an edge set; X represents an initialized entity representation, and Z represents an initialized relationship representation; S23, in order to obtain the structural information of the GO graph, the encoder adds the propagation weight of the GCN layer on the basis of COMPGCN, and uses the inverse edges and relations to represent the extended edges and relations; In S24, in the decoder, the GO graph is regarded as a triple, and the corresponding representation of the triple is used to train the link prediction model; in the training stage, a 1-n scoring strategy is adopted to generate damaged triples by destroying the head term or the tail term, and ConvE is used as the scoring function to provide higher scores for the real triples and lower scores for the damaged triples. The model converges to obtain the embedded representation of the GO terms; S25. After training, the cosine similarity is used to estimate the semantic similarity between entities for the representation of GO terms, and then the GO similarity matrix M is obtained. g .

7. A method for predicting lncRNA function based on graph attention according to any one of claims 1 to 6, characterized in that: The process of constructing a training set based on prior lncRNA-GO functional annotation data described in S3 includes the following steps: First, the lncRNA function annotation file predicted by the lnc-GFP method is obtained, and the lncRNA-GO function annotation pairs in the predicted lncRNA function annotation file are used as positive samples; S32. Randomly construct lncRNA-GO non-functional annotation pairs with the same number as lncRNA-GO functional annotation pairs as negative samples; lncRNA-GO functional annotation pairs and non-functional annotation pairs with the same number as lncRNA-GO functional annotation pairs form a training set.

8. The lncRNA function prediction method based on graph attention according to claim 7, characterized in that: The process of constructing the lncRNA-GO association matrix based on prior lncRNA-GO functional annotation data described in S3 includes the following steps: According to the predicted lncRNA functional annotation file, the lncRNA-GO association matrix was constructed, in which 1 represents the lncRNA-GO functional annotation pair and 0 represents the lncRNA-GO non-functional annotation pair.

9. A computer storage medium, characterized in that The storage medium stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the lncRNA function prediction method based on graph attention as described in any one of claims 1 to 8.

10. A lncRNA function prediction device based on graph attention, characterized in that: The device includes a processor and a memory, wherein at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement a lncRNA function prediction method based on graph attention as described in any one of claims 1 to 8.

Images